Free post-length counter (X, Bluesky, Farcaster, Mastodon, Threads); paid thread split + AI writers
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Full check of one post for a network: valid or not, exact length in that network's unit, remaining, issues (over the limit, byte cap, too many links, invalid characters, NFC) and a "fitted" version cut at a sentence or word boundary with an ellipsis when it is too long. X: weighted, CJK and emoji count 2, every link 23, limit 280. Bluesky: 300 graphemes and 3000 bytes. Farcaster: UTF-8 bytes, 320 per cast (1024 long cast). Mastodon: 500, links 23. Threads (Meta): 500, emoji count as their UTF-8 bytes. For the length alone use the free count_post_length. PAID: $0.001 per call in USDC on Base via x402 over MCP (see payment_options).
The post text (any language)
Optional max length per post in that network's unit; default is the network's own limit (see network_rules)
Target network: x (X/Twitter, default), bluesky, farcaster, mastodon or meta-threads (Threads by Meta)
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http thread-kit https://thread-kit.agent-arena-base.workers.dev/mcp
Full check of one post for a network: valid or not, exact length in that network's unit, remaining, issues (over the limit, byte cap, too many links, invalid characters, NFC) and a "fitted" version cut at a sentence or word boundary with an ellipsis when it is too long. X: weighted, CJK and emoji count 2, every link 23, limit 280. Bluesky: 300 graphemes and 3000 bytes. Farcaster: UTF-8 bytes, 320 per cast (1024 long cast). Mastodon: 500, links 23. Threads (Meta): 500, emoji count as their UTF-8 bytes. For the length alone use the free count_post_length. PAID: $0.001 per call in USDC on Base via x402 over MCP (see payment_options).
| Argument | Type | Description |
|---|---|---|
| text* | string | The post text (any language) |
| limit | integer | Optional max length per post in that network's unit; default is the network's own limit (see network_rules) |
| network | string | Target network: x (X/Twitter, default), bluesky, farcaster, mastodon or meta-threads (Threads by Meta) |
{
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The post text (any language)"
},
"limit": {
"type": "integer",
"description": "Optional max length per post in that network's unit; default is the network's own limit (see network_rules)"
},
"network": {
"enum": [
"x",
"bluesky",
"farcaster",
"mastodon",
"meta-threads"
],
"type": "string",
"description": "Target network: x (X/Twitter, default), bluesky, farcaster, mastodon or meta-threads (Threads by Meta)"
}
},
"additionalProperties": false
}FREE. Exact length of one post for X, Bluesky, Farcaster, Mastodon or Threads (Meta), in that network's own unit, with the limit, remaining and whether it fits. X: weighted, CJK and emoji count 2, every link 23, limit 280. Bluesky: 300 graphemes and 3000 bytes. Farcaster: UTF-8 bytes, 320 per cast (1024 long cast). Mastodon: 500, links 23. Threads (Meta): 500, emoji count as their UTF-8 bytes. Use it before posting; if it does not fit, check_post_length returns a shortened version and split_thread a thread.
| Argument | Type | Description |
|---|---|---|
| text* | string | The post text |
| limit | integer | Optional limit; default is the network's own limit |
| network | string | Target network: x (X/Twitter, default), bluesky, farcaster, mastodon or meta-threads (Threads by Meta) |
{
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The post text"
},
"limit": {
"type": "integer",
"description": "Optional limit; default is the network's own limit"
},
"network": {
"enum": [
"x",
"bluesky",
"farcaster",
"mastodon",
"meta-threads"
],
"type": "string",
"description": "Target network: x (X/Twitter, default), bluesky, farcaster, mastodon or meta-threads (Threads by Meta)"
}
},
"additionalProperties": false
}FREE. Limits, counting units and sources for X, Bluesky, Farcaster, Mastodon and Threads (Meta).
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}FREE. Receiving address, prices and how to pay the paid tools: x402 over MCP (USDC on Base, per call), or the same endpoints over plain HTTP x402 / MPP.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Split long text into a thread where every post fits the network's limit, counted the way that network counts. X: weighted, CJK and emoji count 2, every link 23, limit 280. Bluesky: 300 graphemes and 3000 bytes. Farcaster: UTF-8 bytes, 320 per cast (1024 long cast). Mastodon: 500, links 23. Threads (Meta): 500, emoji count as their UTF-8 bytes. Breaks at paragraph, sentence, clause, then word boundaries (CJK-aware), never inside a URL or @mention, adds n/N numbering that is included in the count, and re-checks every post. Returns posts with their lengths. Pure computation. PAID: $0.002 per call in USDC on Base via x402 over MCP (see payment_options).
| Argument | Type | Description |
|---|---|---|
| text* | string | The text to split (any language, max 25000 characters) |
| limit | integer | Optional max length per post in that network's unit; default is the network's own limit (see network_rules) |
| network | string | Target network: x (X/Twitter, default), bluesky, farcaster, mastodon or meta-threads (Threads by Meta) |
| numbering | string | Where to put "n/N": suffix (default), prefix or none; counted in each post's length |
{
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text to split (any language, max 25000 characters)"
},
"limit": {
"type": "integer",
"description": "Optional max length per post in that network's unit; default is the network's own limit (see network_rules)"
},
"network": {
"enum": [
"x",
"bluesky",
"farcaster",
"mastodon",
"meta-threads"
],
"type": "string",
"description": "Target network: x (X/Twitter, default), bluesky, farcaster, mastodon or meta-threads (Threads by Meta)"
},
"numbering": {
"enum": [
"suffix",
"prefix",
"none"
],
"type": "string",
"description": "Where to put \"n/N\": suffix (default), prefix or none; counted in each post's length"
}
},
"additionalProperties": false
}Turn an article, notes or product description into a 15/30/45/60-second vertical-video script: hook first, then beats with voiceover, on-screen text and a shot description (usable as a text-to-video prompt), plus title, caption, up to 5 hashtags and SRT subtitles. Timed from speaking rate and trimmed to fit (+10%). No video or voice is generated. A failed generation is not charged. PAID: $0.020 per call in USDC on Base via x402 over MCP (see payment_options).
| Argument | Type | Description |
|---|---|---|
| lang | string | Language of voiceover, on-screen text, title and caption: auto = same as the source (default), or en, zh, zh-TW, ja, ko, es, fr, de, pt, ru, id, vi, tr, it. Shot descriptions are in English. |
| text* | string | Source to turn into a script: article, notes or product description (100-3000 characters) |
| tone | string | clear (default), punchy, casual or formal |
| seconds | integer | Target length in seconds: 15, 30 (default), 45 or 60 |
| platform | string | tiktok (default), reels (Instagram Reels) or shorts (YouTube Shorts) |
{
"type": "object",
"required": [
"text"
],
"properties": {
"lang": {
"enum": [
"auto",
"en",
"zh",
"zh-TW",
"ja",
"ko",
"es",
"fr",
"de",
"pt",
"ru",
"id",
"vi",
"tr",
"it"
],
"type": "string",
"description": "Language of voiceover, on-screen text, title and caption: auto = same as the source (default), or en, zh, zh-TW, ja, ko, es, fr, de, pt, ru, id, vi, tr, it. Shot descriptions are in English."
},
"text": {
"type": "string",
"description": "Source to turn into a script: article, notes or product description (100-3000 characters)"
},
"tone": {
"enum": [
"clear",
"punchy",
"casual",
"formal"
],
"type": "string",
"description": "clear (default), punchy, casual or formal"
},
"seconds": {
"enum": [
15,
30,
45,
60
],
"type": "integer",
"description": "Target length in seconds: 15, 30 (default), 45 or 60"
},
"platform": {
"enum": [
"tiktok",
"reels",
"shorts"
],
"type": "string",
"description": "tiktok (default), reels (Instagram Reels) or shorts (YouTube Shorts)"
}
},
"additionalProperties": false
}Turn an article, blog post, notes, changelog or transcript into a ready-to-post thread (hook first, one point per post, wrap-up last) for X, Bluesky, Farcaster, Mastodon or Threads. An open model on Cloudflare Workers AI writes it; Thread Kit re-measures and re-splits every post so each one fits, removes links that are not in the source and flags numbers that are not in it. A failed generation is not charged. PAID: $0.010 per call in USDC on Base via x402 over MCP (see payment_options).
| Argument | Type | Description |
|---|---|---|
| lang | string | Output language: auto = same as the source (default), or en, zh, zh-TW, ja, ko, es, fr, de, pt, ru, id, vi, tr, it |
| text* | string | Source to turn into a thread: article, notes or transcript (100-3000 characters) |
| tone | string | clear (default), punchy, casual or formal |
| posts | integer | Number of posts, 3-12; omit to let the writer choose from the source length |
| platform | string | Target network: x (default), bluesky, farcaster, mastodon or meta-threads |
| numbering | string | Where to put "n/N": suffix (default), prefix or none. Counted in each post's length. |
FREE. A hand-written example of what write_thread_from_article and write_short_video_script return, with the input that produced it. No model call.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 21, 2026.
{
"type": "object",
"required": [
"text"
],
"properties": {
"lang": {
"enum": [
"auto",
"en",
"zh",
"zh-TW",
"ja",
"ko",
"es",
"fr",
"de",
"pt",
"ru",
"id",
"vi",
"tr",
"it"
],
"type": "string",
"description": "Output language: auto = same as the source (default), or en, zh, zh-TW, ja, ko, es, fr, de, pt, ru, id, vi, tr, it"
},
"text": {
"type": "string",
"description": "Source to turn into a thread: article, notes or transcript (100-3000 characters)"
},
"tone": {
"enum": [
"clear",
"punchy",
"casual",
"formal"
],
"type": "string",
"description": "clear (default), punchy, casual or formal"
},
"posts": {
"type": "integer",
"description": "Number of posts, 3-12; omit to let the writer choose from the source length"
},
"platform": {
"enum": [
"x",
"bluesky",
"farcaster",
"mastodon",
"meta-threads"
],
"type": "string",
"description": "Target network: x (default), bluesky, farcaster, mastodon or meta-threads"
},
"numbering": {
"enum": [
"suffix",
"prefix",
"none"
],
"type": "string",
"description": "Where to put \"n/N\": suffix (default), prefix or none. Counted in each post's length."
}
},
"additionalProperties": false
}